Mistral API 429 Too many requests: what it means and how to fix it

What it means

You have exceeded the rate limit for your subscription tier. Requests per second and tokens per minute are enforced independently and apply per organization.

Causes

• Too many requests per second
• Token-per-minute quota exceeded
• Concurrent request limit reached

How to fix it

1. 1
   Fix 1.

   Implement exponential backoff and check the Retry-After response header.

   Snippet

   Copy

   import time
   import random
   from mistralai.client import Mistral
   
   client = Mistral(api_key="YOUR_API_KEY")
   
   def call_with_retry(func, max_retries=5):
       for attempt in range(max_retries):
           try:
               return func()
           except Exception as e:
               if attempt == max_retries - 1:
                   raise
               wait = (2 ** attempt) + random.uniform(0, 1)
               time.sleep(wait)

2. 2
   Fix 2.

   Monitor the X-RateLimit-Remaining response header and check your current limits on the admin limits page.

3. 3
   Fix 3.

   For sustained high throughput, use batch processing (it does not count against real-time rate limits) or upgrade your plan.